KR-20260064218-A - ACCOUNTING PREDICTION SYSTEM AND ACCOUNTING PREDICTION METHOD USING THEREOF

KR20260064218AKR 20260064218 AKR20260064218 AKR 20260064218AKR-20260064218-A

Abstract

The present invention relates to an accounting forecasting system and an accounting forecasting method using the same. An accounting forecasting method according to an embodiment disclosed in the present invention comprises: a transaction data loading step in which at least one of a server and a user terminal loads transaction data; a transaction data preprocessing step in which the transaction data loaded by the server is preprocessed; an evaluation data generation step in which evaluation data is generated based on the transaction data preprocessed by the server; a cash flow forecasting model learning step in which a cash flow forecasting model is learned by the server; and a future cash forecasting step in which future cash is predicted based on the cash flow forecasting model learned by the server.

Inventors

김홍락

Assignees

(주)모두의회계

Dates

Publication Date: 20260507
Application Date: 20241031

Claims (10)

A transaction data loading step in which at least one of the server and the user terminal loads transaction data; A transaction data preprocessing step for preprocessing the transaction data loaded from the above server; Evaluation data generation step for generating evaluation data based on the transaction data preprocessed on the server; A cash flow prediction model training step for training a cash flow prediction model on the above server; and An accounting forecasting method using an accounting forecasting system characterized by including a future cash forecasting step of forecasting future cash based on the cash flow forecasting model learned on the server.
In claim 1, The above transaction data is data recorded in debit and credit, An accounting forecasting method using an accounting forecasting system characterized in that the above transaction data includes a transaction date, a transaction amount, and a transaction type.
In claim 2, The above transaction data preprocessing step is, A transaction data collection step for selectively collecting transaction data of account items satisfying predetermined criteria among the transaction data journalized into debits and credits loaded in the transaction data loading step; A transaction data grouping step for classifying the collected transaction data by business partner; A time series data generation step for generating continuous time series data for each of the transaction data classified by the above business partners; and Accounting forecasting method using an accounting forecasting system characterized by including a variable generation step of adding a time-related variable to at least one of the above transaction data and the above time series data.
In claim 3, An accounting forecasting method using an accounting forecasting system characterized in that the above-mentioned predetermined criteria of the above-mentioned transaction data collection step are accounts receivable, accounts payable, accrued expenses, and deposits.
In claim 3, The above time series data generation step is, An accounting forecasting method using an accounting forecasting system characterized by filling in filler data for dates where no transaction occurred between the first transaction date and the most recent transaction date.
In claim 3, An accounting forecasting method using an accounting forecasting system characterized in that the above time-related variables include at least one of a month, a day of the week, whether it is a holiday, and a time index.
In claim 1, The above evaluation data generation step generates the evaluation data based on the above transaction data that occurred during the evaluation period, and The above evaluation data is an accounting forecasting method using an accounting forecasting system based on a weighted sum of the opportunity cost of predicting the bank balance as a late date and low amount during the forecast period and the inventory cost of predicting the bank balance as an early date and high amount during the forecast period.
In claim 7, An accounting forecasting method using an accounting forecasting system characterized in that the length of the above evaluation period is greater than or equal to the length of the above forecast period.
In claim 3, An accounting forecasting method using an accounting forecasting system, characterized in that the above cash flow forecasting model learning step learns the pattern of increase or decrease in cash for each business partner through the transaction data classified by business partner in the above data preprocessing step, and learns using a TFT (Temporal Fusion Transformer) model that predicts the daily bank account amount during the forecasting period by reflecting multiple variables generated by the transaction data.
In claim 1, The above future cash is projected by adding estimated cash sales and expected collections to current cash, and subtracting estimated payments and expected cash costs. An accounting forecasting method using an accounting forecasting system, characterized in that the above cash flow forecasting model learning step learns and estimates the pattern of increase and decrease of the above expected recovery amount and the above expected payment amount.

Description

Accounting Prediction System and Accounting Prediction Method Using Thereof The present invention relates to an accounting forecasting system and an accounting forecasting method using the same, and more specifically, to an accounting forecasting system that forecasts a user's future cash flow by learning and analyzing the user's business activities and an accounting forecasting method using the same. Accounting activities are necessary, such as calculating revenue and expenses to determine profit and loss or paying taxes accordingly. These accounting activities are essential for individuals or businesses to carry out economic activities (e.g., paying taxes, formulating management strategies, disclosing accounting data in accordance with obligations, etc.). Meanwhile, in accounting activities, it is important to forecast cash flow and establish management strategies accordingly at an early stage. However, traditionally, the methods used to forecast such cash flow were inaccurate, which posed a problem as it was not beneficial for formulating management strategies. Therefore, technology is needed to estimate cash flow through the user's past business activities and accurately predict future account balances. FIG. 1 is a conceptual diagram of an accounting forecasting system in which an accounting forecasting method according to an embodiment disclosed in the present invention is performed. FIG. 2 illustrates an artificial neural network model and the operation of each neuron related to artificial intelligence learning performed in some steps of an accounting forecasting method according to an embodiment of the present invention. FIG. 3 illustrates the training and inference of an artificial neural network performed in some steps of an accounting forecasting method according to an embodiment disclosed in the present invention. FIG. 4 is a detailed conceptual diagram of a server, which is a component of an accounting forecasting system in which an accounting forecasting method according to an embodiment disclosed of the present invention is performed. FIG. 5 is a schematic flowchart of an accounting forecasting method according to a disclosed embodiment of the present invention. FIG. 6 is a detailed flowchart of the transaction data preprocessing step of the accounting forecasting method according to the disclosed embodiment of the present invention. FIG. 7 is a detailed flowchart of the future cash forecasting step of the accounting forecasting method according to an embodiment of the present invention. Hereinafter, an accounting forecasting system according to one embodiment of the present invention and an accounting forecasting method using the same will be described in detail with reference to the attached drawings. It should be noted that when assigning reference numerals to the components of each drawing, the same components are assigned the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the embodiments of the present invention, if it is determined that a detailed description of related known components or functions would hinder understanding of the embodiments of the present invention, such detailed description is omitted. In describing the components of the embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended merely to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by these terms. Furthermore, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application. FIG. 1 is a conceptual diagram of an accounting forecasting system (1) in which an accounting forecasting method according to an embodiment disclosed in the present invention is performed. Referring to FIG. 1, an accounting forecasting system (1) in which an accounting forecasting method according to an embodiment disclosed in the present invention is performed may include a user terminal (100) and a server (200). The user terminal (100) may be a means for a user (U100) to communicate with the server (200). For example, the user terminal (100) may be a device capable of computation and communication, such as a mobile phone terminal, a PC, or a tablet. The user terminal (100) may include an input unit (not shown) for receiving various information from the user (U100). For example, the input unit of the user terminal (100) may be at least one of various input devices including a keyboard, a mouse, a touch screen, etc. The de